NBA Data Analysis

Load data

ranking = read.csv("/Users/georgegasparis/GitHub/GraphBasketAnalysis/Data/ranking.csv")
teams = read.csv("/Users/georgegasparis/GitHub/GraphBasketAnalysis/Data/teams.csv")
player = read.csv("/Users/georgegasparis/GitHub/GraphBasketAnalysis/Data/players.csv")
games = read.csv("/Users/georgegasparis/GitHub/GraphBasketAnalysis/Data/games.csv")
games_details = read.csv("/Users/georgegasparis/GitHub/GraphBasketAnalysis/Data/games_details.csv")

Show data

head(games_details,10)

Load main library

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.3.3     ✓ purrr   0.3.4
## ✓ tibble  3.0.4     ✓ dplyr   1.0.2
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.0

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

Group by player’s name

games_details %>% group_by(GAME_ID)

Points vs minutes played

ggplot(data = games_details, mapping = aes( x = MIN, y = PTS, color = START_POSITION, shape = START_POSITION)) +
  geom_point()

## Warning: Removed 92261 rows containing missing values (geom_point).

#### Specify a condition

ggplot(data = games_details, mapping = aes(x = MIN, y = PTS, color = TEAM_ABBREVIATION == "MIL")) +
  geom_point()

## Warning: Removed 92261 rows containing missing values (geom_point).

games_details %>%
  filter(TEAM_ABBREVIATION=="MIL") %>%
  ggplot() + geom_point( mapping = aes(x = MIN, y = PTS, color = START_POSITION))

## Warning: Removed 3080 rows containing missing values (geom_point).

select(games_details, MIN, FGM, FGA)